Making neural networks more neural
Abstract
Deep neural networks (DNNs) are practical and effective but, despite the name, they lack biological validity. The recent study by Kang et al. 1 in Patterns takes a step toward rectifying this deficit by hard-wiring receptive fields into the first layer of a visual DNN, and the authors show that their network can generalize across image types. Training on photographs, for example, resulted in good performance on sketches; conventional DNNs did not match this behavior.
Fields of Study & Subjects
Neural Networks and Applications
Advanced Neural Network Applications
Visual perception and processing mechanisms
Publication details
- Journal / source
- Patterns
- Volume
- 7
- Issue
- 2
- Pages
- 101494–101494
- Publication date
- 1 February 2026
- Language
- EN